ChatGPT and Knowledge Management

Arnold Kling, Stan Garfield, and Dennis Pearce discuss how the ChatGPT digestion system works, what it means for knowledge management at large firms and what it means for knowledge work in general. Note that participants were using ChatGPT in real time to illustrate points and find answers to questions

[@arnoldsk]

Here is the chat file if you want to follow along: 20:05:06 From Chitwood, Ami : DEC 20:05:47 From Dennis P Waters : PDP-11! 20:05:52 From Chitwood, Ami : 😀 Stan's forgotten more about KM than the rest of us! 20:06:06 From Jennilyn Wiley (Auburn University) : Reacted to "😀 Stan's forgotten ..." with ❤ 20:07:20 From Stan Garfield : My KM site sites.google.com/site/stangarfield/ 20:07:53 From Tom Grey : Reacted to "My KM site s..." with 👍 20:14:30 From Stan Garfield : I just asked: what should i get my wife for valentines day? The ideal Valentine's Day gift for your wife depends on her personal preferences, but some popular options include: Jewelry, such as a necklace, bracelet, or earrings A bouquet of her favorite flowers A romantic getaway or a staycation A spa day or massage A cooking or baking class A sentimental item, such as a photo album or custom-made keepsake A book or movie she has been wanting to read/watch A thoughtful piece of home decor Remember, the most important part is showing your love and appreciation for her, so choose a gift that fits her unique personality and interests. 20:15:46 From Bart Verheijen : Reacted to "I just asked: what s..." with 👍 20:19:53 From Barbara : I have found Viva Topics (part of the Microsoft Viva suite) to have a similar approach. The AI "suggests" a lot and users are expected to answer question like "is this correct"? Then the AI learns, I guess. 20:20:40 From Chitwood, Ami : It does not perform references interviews. 20:25:15 From Chitwood, Ami : Solving search... 20:27:27 From Jennilyn Wiley (Auburn University) : it wou;d be great if it cited sources 20:28:27 From Bart Verheijen : You can ask it to give (links to) sources 20:28:44 From Bart Verheijen : but they do tend to be wrong or sometimes non-existent 20:28:50 From Tom Grey : Replying to "it wou;d be great if..." I think it's statistical token analysis is not like usual human sources, like wiki. 20:29:07 From Stan Garfield : knowledge.wharton.upenn.edu/podcast/wharton-business-daily-podcast/chatgpt-passed-an-mba-exam-whats-next/ 20:29:07 From Jennilyn Wiley (Auburn University) : Reacted to "but they do tend to ..." with 👍 20:34:07 From Stan Garfield : My document on the 32 KM components and ChatGPT 1drv.ms/w/s!Aioueb8G-fzngcQe79exETEFPnz0pA?e=gN1mA4 20:34:23 From Jennilyn Wiley (Auburn University) : just like librarians have helped people figure out search strings to be efficient and effective, that will transition to how to best write and refine prompts. A good prompt for chatGPT makes all the difference 20:35:43 From Chitwood, Ami : ^Jennilyn - 100% and the ability to evaluate results 20:36:00 From Jennilyn Wiley (Auburn University) : yes, chatGPT told me it is not able to evaluate results 20:36:55 From Jennilyn Wiley (Auburn University) : SEO for AI 20:37:59 From Chitwood, Ami : Just like you can manipulate social media (e.g., having a error) to increase chances for "viral," I predict that there will be ChatGPT stuffing/manipulations.... 20:40:12 From Bill Kaplan : Always trust but verify..always 20:40:28 From Jennilyn Wiley (Auburn University) : Reacted to "Always trust but ver..." with 👍 20:40:33 From Chitwood, Ami : Reacted to "Always trust but ver..." with 👍 20:40:35 From Tom Grey : Reacted to "Always trust but ver..." with 👍 20:42:24 From Bart Verheijen : Reacted to "Always trust but ver..." with 👍 20:42:32 From Bill Kaplan : I have a 1908 Keuffel and Esser slide rule 20:45:14 From JC Monney : Correct it odes not have context 20:45:53 From JC Monney : you ned to provide GPT with your context. It is not good (yet) at asking context 20:46:13 From Bill Kaplan : Reacted to "you ned to provide G..." with 👍🏻 20:47:08 From Barbara : In addition to providing context, it helps to ask good questions or at least try to ask the question in different ways to get slightly different answers. 20:49:10 From JC Monney : Viva Topics works best with 100,000 documents 20:49:19 From Barbara : Reacted to "Viva Topics works be..." with 👍 20:49:21 From Chitwood, Ami : Imagine...looking in all of our personal KM systems? (OneDrive, Teams, Email...) 20:49:43 From Tom Grey : Reacted to "Viva Topics works be..." with 👍 20:49:51 From Jennilyn Wiley (Auburn University) : i'd love to know in the black box how it determines expertise. since it's probabilistic, is it just looking at volume? (e.g., the more prolific a writer, the more weight it gives their source info) 20:49:56 From Barbara : Viva Topics and intranets also need to be relatively "clean" for this to work. 20:50:12 From JC Monney : they will provide API to you enterprise content 20:50:18 From Bill Kaplan : A key for GPT is to provide the right best context in the query and as you engage with chat GPT. I have found that the better the context for the Q and the A the better the outcome for your query 20:50:43 From JC Monney : deep mind 20:51:09 From Bart Verheijen : Replying to "Viva Topics and intr..." clean meaning no duplicates or the content within the topics being true or verified? 20:51:43 From Stan Garfield : Constitutional AI refers to the use of artificial intelligence (AI) systems and technologies in accordance with the principles, values, and laws that are enshrined in a nation's constitution. This approach involves the development, deployment, and use of AI in a manner that aligns with the fundamental rights and freedoms guaranteed by the constitution. It aims to ensure that AI is used ethically, responsibly, and transparently, while also protecting the privacy and human rights of citizens. 20:52:06 From Bill Kaplan : I believe Microsoft is going to announce tomorrow or next day how chat GPT has been integrated into Edge. 20:54:49 From Bart Verheijen : Google news today: We’ve been working on an experimental conversational AI service, powered by LaMDA, that we’re calling Bard. 20:54:50 From Barbara : Bing already separates the external search from internal system search, so I look forward to seeing how ChatGPT will be integrated in Bing. 20:55:04 From Bart Verheijen : blog.google/technology/ai/bard-google-ai-search-updates/ 20:55:36 From Tom Grey : Reacted to "blog.google/..." with 👍 20:56:34 From Tom Grey : analyticsindiamag.com/openai-rival-anthropic-starts-claude-early-access/ 20:57:24 From Bill Kaplan : The non disclosure issue reminds me about the original discussions and concerns with CoPs about what can be discussed online. within an organzation 20:57:35 From Barbara : Reacted to "The non disclosure i..." with 👍 20:57:44 From Jennilyn Wiley (Auburn University) : www.cnn.com/2022/10/21/tech/artists-ai-images/index.html 20:58:18 From Jennilyn Wiley (Auburn University) : Artists not happy about their art being used to train Open AI. I believe Getty sued. 20:58:30 From Bart Verheijen : Reacted to "Artists not happy ab..." with 👍 20:59:23 From Jennilyn Wiley (Auburn University) : www.cnn.com/2023/01/17/tech/getty-images-stability-ai-lawsuit/index.html 20:59:27 From Bart Verheijen : Replying to "Artists not happy ab..." Thanks! That's basically artists requesting their (creative) work be removed or excluded from the training set; and thereby from the responses 20:59:53 From Tim Wood Powell : All of this is a huge rip off of the content creators! Information is created by people who get paid to do it - this is just a way to “reuse” this on a massive scale - without attribution or [ayment! 20:59:54 From Barbara : Knowledge graph+ChatGPT for internal use? 20:59:56 From Bill Kaplan : Thank you for this time 21:00:04 From Jennilyn Wiley (Auburn University) : Reacted to "All of this is a hug..." with 👍 21:00:30 From Dennis P Waters : Lord help us if financial institutions decide to use this for enterprise risk management 21:00:31 From JC Monney : thank you for the invite and great sharing 21:00:34 From Dennis Pearce : www.aistudy.com/paper/aaai_journal/AIMag10-02-002.pdf 21:00:57 From Chitwood, Ami : Right on - I remember when excel came to the workplace...people are still here 🤓 21:01:06 From Jennilyn Wiley (Auburn University) : Reacted to "Right on - I remembe..." with 😂 21:01:09 From Tom Grey : Reacted to "Knowledge graph+Chat..." with 👍 21:01:53 From Jennilyn Wiley (Auburn University) : +1 Ami - disruptive and changing but not necessarily career ending

[@ch3ssmast3r3]

What is thinking but the process of digesting information and comparing the previous x amount of experiences or knowledge about sed topic and creating an answer.

[@arnoldsk]

I guess I would say that humans pay attention to the information contained in the words that we see. These models ignore this information and just look at a sequence of tokens. To me, this seems like qualitatively less thinking.